© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 17-GEMMASCOPE-RES-16K
    11. 4426
    Prev
    Next
    INDEX
    Explanations

    technical terms and symbols commonly used in mathematical and scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .
    -0.81
    ,
    -0.70
     in
    -0.56
     on
    -0.53
     
    -0.52
     -
    -0.51
     of
    -0.51
     co
    -0.48
     at
    -0.48
    ↵
    -0.47
    POSITIVE LOGITS
    GraphicsUnit
    1.27
    BeginContext
    1.23
     Efq
    1.15
    DoubleQuotes
    1.11
     ſind
    1.10
     ContentValues
    1.08
     Roskov
    1.06
     pleaſure
    1.06
    ⓧ
    1.05
     Majefty
    1.03
    Activations Density 1.322%

    No Known Activations